game-art-direction
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional text and design guidelines. It does not contain any executable scripts, binary files, or network-active components.\n- [DATA_EXPOSURE_AND_EXFILTRATION]: Instructions in SKILL.md explicitly state that the art direction phase should not include details about vendors, models, interfaces, or secret key schemes, preventing accidental credential exposure.\n- [REMOTE_CODE_EXECUTION]: There are no patterns of remote code execution, package installations, or external script downloads in the skill instructions or reference files.\n- [PROMPT_INJECTION]: The skill uses professional, role-based instructions without any attempts to bypass safety filters or override system-level constraints.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external design documents (GAME_DESIGN.md and PRODUCT_BRIEF.md). While this represents a data ingestion surface, the skill lacks dangerous capabilities such as network access or shell execution that could be exploited through malicious content in those files.\n
- Ingestion points: GAME_DESIGN.md and PRODUCT_BRIEF.md referenced in SKILL.md.\n
- Boundary markers: Uses structured design steps to extract specific information.\n
- Capability inventory: The skill is limited to generating markdown documentation (ART_DIRECTION.md and VISUAL_TARGETS.md).\n
- Sanitization: Not applicable as the output is static text intended for human review.
Audit Metadata